Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study

• URL: http://arxiv.org/abs/2509.05553v1
• Date: Sat, 06 Sep 2025 00:44:34 GMT
• Title: Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study
• Authors: Serge Lionel Nikiema, Jordan Samhi, Micheline Bénédicte Moumoula, Albérick Euraste Djiré, Abdoul Kader Kaboré, Jacques Klein, Tegawendé F. Bissyandé,
• Abstract summary: This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns.<n>The authors propose bidirectional reasoning, the ability to apply transformations in both directions without being explicitly trained on the reverse direction.<n>Experiments demonstrated that CFT successfully achieved bidirectional reasoning, enabling strong reverse performance while maintaining forward task capabilities.
• Score: 10.4691578575499
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns. The authors propose bidirectional reasoning,the ability to apply transformations in both directions without being explicitly trained on the reverse direction, as a test for genuine understanding. They argue that true comprehension should naturally allow reversibility. For example, a model that can change a variable name like userIndex to i should also be able to infer that i represents a user index without reverse training. The researchers tested current language models and discovered what they term cognitive specialization: when models are fine-tuned on forward tasks, their performance on those tasks improves, but their ability to reason bidirectionally becomes significantly worse. To address this issue, they developed Contrastive Fine-Tuning (CFT), which trains models using three types of examples: positive examples that maintain semantic meaning, negative examples with different semantics, and forward-direction obfuscation examples. This approach aims to develop deeper understanding rather than surface-level pattern recognition and allows reverse capabilities to develop naturally without explicit reverse training. Their experiments demonstrated that CFT successfully achieved bidirectional reasoning, enabling strong reverse performance while maintaining forward task capabilities. The authors conclude that bidirectional reasoning serves both as a theoretical framework for assessing genuine understanding and as a practical training approach for developing more capable AI systems.

Related papers

• Learning a Dense Reasoning Reward Model from Expert Demonstration via Inverse Reinforcement Learning [50.20267980386502]
  We learn a dense, token-level reward model for process supervision directly from expert demonstrations.<n>The learned reasoning reward serves two complementary roles: (i) it provides step-level feedback to optimise a reasoning policy during training; and (ii) it functions at inference as a critic to rerank sampled traces under fixed compute budgets.
  arXiv  Detail & Related papers  (2025-10-02T09:55:26Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• Implicit Reasoning in Transformers is Reasoning through Shortcuts [10.351525484558376]
  Test-time compute is emerging as a new paradigm for enhancing language models' complex multi-step reasoning capabilities.<n>We investigate how language models perform implicit reasoning in multi-step tasks.
  arXiv  Detail & Related papers  (2025-03-10T17:58:31Z)
• Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs [28.565225092457897]
  Reinforcement learning can drive self-improvement in language models on verifiable tasks.<n>We find that Qwen-2.5-3B far exceeds Llama-3.2-3B under identical RL training for the game of Countdown.<n>Our study reveals that Qwen naturally exhibits these reasoning behaviors, whereas Llama initially lacks them.
  arXiv  Detail & Related papers  (2025-03-03T08:46:22Z)
• Bidirectional Awareness Induction in Autoregressive Seq2Seq Models [47.82947878753809]
  Bidirectional Awareness Induction (BAI) is a training method that leverages a subset of elements in the network, the Pivots, to perform bidirectional learning without breaking the autoregressive constraints. In particular, we observed an increase of up to 2.4 CIDEr in Image-Captioning, 4.96 BLEU in Neural Machine Translation, and 1.16 ROUGE in Text Summarization compared to the respective baselines.
  arXiv  Detail & Related papers  (2024-08-25T23:46:35Z)
• Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training [57.771940716189114]
  We show that large language models (LLMs) suffer from the "reversal curse" The root cause of the reversal curse lies in the different word order between the training and inference stage. We propose Semantic-aware Permutation Training (SPT) to address this issue.
  arXiv  Detail & Related papers  (2024-03-01T18:55:20Z)
• ReAct: Synergizing Reasoning and Acting in Language Models [44.746116256516046]
  We show that large language models (LLMs) can generate both reasoning traces and task-specific actions in an interleaved manner. We apply our approach, named ReAct, to a diverse set of language and decision making tasks. ReAct overcomes issues of hallucination and error propagation prevalent in chain-of-thought reasoning by interacting with a simple Wikipedia API.
  arXiv  Detail & Related papers  (2022-10-06T01:00:32Z)
• Prediction or Comparison: Toward Interpretable Qualitative Reasoning [16.02199526395448]
  Current approaches use either semantics to transform natural language inputs into logical expressions or a "black-box" model to solve them in one step. In this work, we categorize qualitative reasoning tasks into two types: prediction and comparison. In particular, we adopt neural network modules trained in an end-to-end manner to simulate the two reasoning processes.
  arXiv  Detail & Related papers  (2021-06-04T10:27:55Z)
• Unnatural Language Inference [48.45003475966808]
  We find that state-of-the-art NLI models, such as RoBERTa and BART, are invariant to, and sometimes even perform better on, examples with randomly reordered words. Our findings call into question the idea that our natural language understanding models, and the tasks used for measuring their progress, genuinely require a human-like understanding of syntax.
  arXiv  Detail & Related papers  (2020-12-30T20:40:48Z)
• Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision [57.14468881854616]
  We propose an auxiliary training objective that improves the generalization capabilities of neural networks. We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task. Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
  arXiv  Detail & Related papers  (2020-04-20T02:47:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.